arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2303.15022cs.AIcs.MA
收藏

通过论辩式交流实现冲突解决的交互式解释

Interactive Explanations by Conflict Resolution via Argumentative Exchanges

Imperial College London(帝国理工学院)

Antonio Rago, Hengzhi Li, Francesca Toni

AI总结:

针对XAI领域现有研究多聚焦静态解释的问题,提出基于计算论辩的论辩式交流(AXs)框架,用于智能体间冲突解决,分析其理论特性并通过模拟实验验证不同智能体行为的冲突解决效果。

摘要:

随着可解释人工智能(XAI)领域日趋成熟,对AI模型(输出)的交互式解释的需求不断增长,但当前前沿研究大多聚焦于静态解释。本文转而借助计算论辩,将交互式释界定为智能体(即AI模型和/或人类)之间的冲突解决过程。具体而言,我们定义了论辩式交流(Argumentative eXchanges, AXs),用于在多智能体系统中动态共享各智能体量化双极论辩框架中承载的信息,以解决智能体间的冲突。随后我们将AXs应用于XAI场景:机器与人类围绕机器的预测展开交互。我们识别并评估了适用于XAI的AXs的若干理论特性。最后,我们通过定义多种智能体行为(例如捕捉机器中的反事实推理模式、凸显人类认知偏差的影响),为XAI场景实例化了AXs。我们(在模拟环境中)通过实验证明了这些行为在冲突解决方面的比较优势,并表明最强的论证未必总是最有效的。

英文摘要:

As the field of explainable AI (XAI) is maturing, calls for interactive explanations for (the outputs of) AI models are growing, but the state-of-the-art predominantly focuses on static explanations. In this paper, we focus instead on interactive explanations framed as conflict resolution between agents (i.e. AI models and/or humans) by leveraging on computational argumentation. Specifically, we define Argumentative eXchanges (AXs) for dynamically sharing, in multi-agent systems, information harboured in individual agents' quantitative bipolar argumentation frameworks towards resolving conflicts amongst the agents. We then deploy AXs in the XAI setting in which a machine and a human interact about the machine's predictions. We identify and assess several theoretical properties characterising AXs that are suitable for XAI. Finally, we instantiate AXs for XAI by defining various agent behaviours, e.g. capturing counterfactual patterns of reasoning in machines and highlighting the effects of cognitive biases in humans. We show experimentally (in a simulated environment) the comparative advantages of these behaviours in terms of conflict resolution, and show that the strongest argument may not always be the most effective.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑